whitepaper 0.0.1 → 0.0.2

data/lib/whitepaper/cli.rb

@@ -3,11 +3,14 @@ require 'optparse'
 require 'whitepaper'
 
 module Whitepaper
+  # The commandline interface to Whitespace.
   class CLI
+    # Usage banner
     BANNER = <<-USAGE
     USAGE
 
     class << self
+      # Parse and respond to the command line options.
       def parse_options
         options = {}
         @opts = OptionParser.new do |opts|
@@ -77,6 +80,7 @@ module Whitepaper
         end
       end
 
+      # Executes the command line version of whitespace.
       def CLI.run
         begin
           parse_options
@@ -85,11 +89,6 @@ module Whitepaper
           exit -1
         end
 
-        def fail
-          puts @opts
-          exit -1
-        end
-
         # Default
         puts BANNER
         exit 0

data/lib/whitepaper/engine/citeseerx.rb

@@ -4,15 +4,21 @@ require 'whitepaper/paper'
 
 module Whitepaper
   module Engine
+    # This engine uses the CiteSeerX database to query metadata about a paper.
     module CiteSeerX
+      # The domain to use for CiteSeerX.
       DOMAIN = "http://citeseerx.ist.psu.edu"
+
+      # The url to use to search by title.
       SEARCH_BY_TITLE_URL = "search?q=title%3A{title}&t=doc&sort=cite"
 
       class << self
+        # Returns a url that will query for the given title keywords.
         def find_by_title_url(title)
           "#{DOMAIN}/#{SEARCH_BY_TITLE_URL.gsub(/\{title\}/, title)}"
         end
 
+        # Returns a Whitespace::Paper by searching for the paper with the given title keywords.
         def find_by_title(title)
           @agent = Mechanize.new
           page = @agent.get "#{find_by_title_url(title)}"
@@ -25,25 +31,26 @@ module Whitepaper
           retrieve_details paper_link
         end
 
+        # Returns a Whitespace::Paper by reading the direct page for a particular paper.
         def retrieve_details(url)
           @agent = Mechanize.new
 
           page = @agent.get url
 
-          def get_meta(name, page)
+          get_meta = lambda {|name|
             meta = page.search "//meta[@name=\"#{name}\"]"
             if meta.nil? or meta.first.nil?
               return ""
             end
             meta.first.attribute "content"
-          end
-
-          description = get_meta("description", page)
-          keywords_raw = get_meta("keywords", page)
-          title = get_meta("citation_title", page)
-          authors_raw = get_meta("citation_authors", page)
-          year = get_meta("citation_year", page)
-          conference = get_meta("citation_conference", page)
+          }
+
+          description = get_meta.call("description")
+          keywords_raw = get_meta.call("keywords")
+          title = get_meta.call("citation_title")
+          authors_raw = get_meta.call("citation_authors")
+          year = get_meta.call("citation_year")
+          conference = get_meta.call("citation_conference")
 
           authors = authors_raw.to_s.split(',').map(&:strip)
           keywords = keywords_raw.to_s.split(',').map(&:strip)

data/lib/whitepaper/engine/google.rb

@@ -4,8 +4,10 @@ require 'whitepaper/paper'
 
 module Whitepaper
   module Engine
+    # This engine simply uses a google filetype:pdf search to find paper information.
     module Google
       class << self
+        # Finds a Whitespace::Paper by looking up a paper with the given title keywords.
         def find_by_title(title)
           @agent = Mechanize.new
 

data/lib/whitepaper/paper.rb

@@ -1,15 +1,32 @@
 module Whitepaper
+  # The representation of a paper, including title, author, and pdf urls.
   class Paper
+    # The title of the paper.
     attr_reader :title
+
+    # The list of authors of the paper.
     attr_reader :authors
+
+    # A summary of the paper, typically an abstract. Defaults to "".
     attr_reader :description
+
+    # A list of keywords associated with the paper. Defaults to [].
     attr_reader :keywords
+
+    # The year of publication. Defaults to "".
     attr_reader :year
+
+    # The conference, if any, the paper appeared. Defaults to "".
     attr_reader :conference
 
+    # A list of urls to pdf copies of the paper. Defaults to [].
     attr_reader :pdf_urls
+
+    # A list of urls to ps copies of the paper. Defaults to [].
     attr_reader :ps_urls
 
+    # Construct an object representing paper metadata with the given fields.
+    # Title and authors are required, all other fields can be omitted.
     def initialize(title, authors, options = {})
       @title = title
       @authors = authors
@@ -22,6 +39,9 @@ module Whitepaper
       @ps_urls = options[:ps_urls] || []
     end
 
+    # Downloads the paper by using the pdf urls. The created file will be named
+    # after the title if no filename is given. The file will overwrite any existing
+    # file with the same name in the current directory.
     def download(filename = nil)
       if filename.nil?
         filename = title.to_s
@@ -50,6 +70,7 @@ module Whitepaper
       true
     end
 
+    # Output a simple description of the paper metadata.
     def to_s
       "Title:       #{@title}\n" +
       "Authors:     #{@authors}\n" +

data/lib/whitepaper/version.rb

@@ -1,3 +1,4 @@
 module Whitepaper
-  VERSION = "0.0.1"
+  # Version number for Whitepaper gem.
+  VERSION = "0.0.2"
 end

data/lib/whitepaper.rb

@@ -3,8 +3,14 @@ require "whitepaper/version"
 require 'whitepaper/engine/citeseerx'
 require 'whitepaper/engine/google'
 
+# The namespace for the available metadata gathering engines.
+module Whitepaper::Engine
+end
+
+# The main module encapsulating Whitepaper resources.
 module Whitepaper
   class << self
+    # Find and return a Whitepaper::Paper by searching for a partial match with the given title.
     def find_by_title(title)
       paper = Engine::CiteSeerX.find_by_title(title)
 
@@ -24,6 +30,7 @@ module Whitepaper
       paper
     end
 
+    # Find and return a list of authors by searching for a partial match with the given title.
     def find_authors_by_title(title)
       paper = find_by_title(title)
 
@@ -32,6 +39,7 @@ module Whitepaper
       end
     end
 
+    # Find and return the proper title by searching for a partial match with the given title.
     def find_title_by_title(title)
       paper = find_by_title(title)
 
@@ -40,6 +48,7 @@ module Whitepaper
       end
     end
 
+    # Find and return a list of pdf urls by searching for a partial match with the given title.
     def find_pdfs_by_title(title)
       paper = find_by_title(title)
 
@@ -48,6 +57,8 @@ module Whitepaper
       end
     end
 
+    # Downloads the first available pdf by searching for a partial match with the given title.
+    # The name of the file will be the title of the paper.
     def download_pdf_by_title(title)
       paper = find_by_title(title)
       paper.download

data/whitepaper.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |gem|
   gem.email         = ["wilkie05@gmail.com"]
   gem.description   = %q{Finds metadata on scholarly works and is able to download pdfs of whitepapers.}
   gem.summary       = %q{Finds whitepaper metadata and pdf download links with a basic keyword query using web-based databases such as Google and CiteSeerX.}
-  gem.homepage      = ""
+  gem.homepage      = "https://github.com/wilkie/whitepaper"
 
   gem.files         = `git ls-files`.split($/)
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: whitepaper
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-01-27 00:00:00.000000000 Z
+date: 2013-01-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -61,11 +61,10 @@ files:
 - lib/whitepaper/cli.rb
 - lib/whitepaper/engine/citeseerx.rb
 - lib/whitepaper/engine/google.rb
-- lib/whitepaper/finder.rb
 - lib/whitepaper/paper.rb
 - lib/whitepaper/version.rb
 - whitepaper.gemspec
-homepage: ''
+homepage: https://github.com/wilkie/whitepaper
 licenses: []
 post_install_message: 
 rdoc_options: []

data/lib/whitepaper/finder.rb

@@ -1,4 +0,0 @@
-module Whitepaper
-  class Finder
-  end
-end